Instructions to use tgsc/debertina-base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use tgsc/debertina-base with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("tgsc/debertina-base", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -21,7 +21,7 @@ DeBERTina é um modelo [DeBERTa-v3](https://arxiv.org/abs/2111.09543) em portugu
|
|
| 21 |
|
| 22 |
*DeBERTina is a portuguese [DeBERTa-v3](https://arxiv.org/abs/2111.09543) model trained electra-style [ELECTRA](https://arxiv.org/abs/2003.10555) (with Replaced Token Detection - RTD) and gradient-disentangled embedding sharing (GDES).*
|
| 23 |
|
| 24 |
-
| Model | type | Vocabulary | Parameters | Context
|
| 25 |
| :-: | :-: | :-: | :-: | :-: |
|
| 26 |
| [ult5-pt-small](https://huggingface.co/tgsc/ult5-pt-small) | encoder-decoder | 65k |82.4M | 1024 |
|
| 27 |
| [sentence-transformer-ult5-pt-small](https://huggingface.co/tgsc/ult5-pt-small) | sentence-transformer | 65k | 51M | 1024 |
|
|
|
|
| 21 |
|
| 22 |
*DeBERTina is a portuguese [DeBERTa-v3](https://arxiv.org/abs/2111.09543) model trained electra-style [ELECTRA](https://arxiv.org/abs/2003.10555) (with Replaced Token Detection - RTD) and gradient-disentangled embedding sharing (GDES).*
|
| 23 |
|
| 24 |
+
| Model | type | Vocabulary | Parameters | Context length |
|
| 25 |
| :-: | :-: | :-: | :-: | :-: |
|
| 26 |
| [ult5-pt-small](https://huggingface.co/tgsc/ult5-pt-small) | encoder-decoder | 65k |82.4M | 1024 |
|
| 27 |
| [sentence-transformer-ult5-pt-small](https://huggingface.co/tgsc/ult5-pt-small) | sentence-transformer | 65k | 51M | 1024 |
|